Talk:Lilliefors test
 | This article is rated Stub-class on Wikipedia's content assessment scale. It is of interest to the following WikiProjects: | ||||||||||
| |||||||||||
Inline citations
[edit]I just added a {{No footnotes}} template. I know there isn't much here, but is it all in the original paper by Lilliefors? I can't really tell without inline citations. The bit that most bothers me is "There is an extensive literature on normality testing, but as a practical matter many experienced data analysts sidestep formal testing and assess the feasibility of a normal model by using a graphical tool such as a Q-Q plot." Yaris678 (talk) 20:45, 28 October 2010 (UTC)
Focus on normality testing
[edit]Given that the KS test is often mis-applied, it would be beneficial to note that Lilliefors modified KS test is not exclusive to tests for normality. The bias introduced by parameter estimation is also true of other distributions. One example with simulated critical values is given here: http://dx.doi.org/10.1109/JOE.2009.2036947 90.203.246.243 (talk) 23:25, 19 June 2013 (UTC)